图像混合噪声的模糊加权均值滤波算法仿真  

New Efficient Fuzzy Weighted Mean Filter Approach for Removal of Mixed Noise

作　　者：陈大力[1] 薛定宇[1] 高道祥[1] 

机构地区：[1]东北大学人工智能与机器人研究所,沈阳110004

出　　处：《系统仿真学报》2007年第3期527-530,共4页Journal of System Simulation

摘　　要：针对图像混合噪声提出了一种新型的模糊加权均值滤波算法。该算法以象素的灰度差为基础,通过构建T-S模糊模型来自适应地计算反映各象素噪声污染程度的加权系数,然后通过加权平均算法得出最终结果,因此,该算法能够有效地抑制噪声象素对其邻域象素的影响,极大地改善了滤波效果。基于Matlab的多组仿真实验结果表明,该算法具有很好的普遍性和自适应性,能够比较有效地保护细节信息,对混合噪声有很好的抑制能力。A new efficient fuzzy weighted mean filter approach to the restoration of images corrupted by mixed noise was proposed. The coefficient of the proposed method can be varied adaptively based on degree of mixed noise by designing a T-S model based on differences between pixels in the window. Finally, the values of the processed pixel can be calculated. The proposed method can reduce the influences of noise pixels effectively by adjusting the coefficient and improve the filtering performance greatly. Simulation results based on Matlab show that the proposed method can be applied to many different types of image and preserve the integrity of edge and detail information and remove mixed noise effectively.

关 键 词：图像滤波 模糊加权均值 混合噪声 T-S模型 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]